University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Co-evolutionary modular neural networks for automatic problem decomposition

Khare, VR, Yao, X, Sendhoff, B, Jin, Y and Wersing, H (2005) Co-evolutionary modular neural networks for automatic problem decomposition

[img] PDF (deleted)
cec-2005-1-final.pdf
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (405kB)
[img]
Preview
PDF
KhareYaoCEC05.pdf
Available under License : See the attached licence file.

Download (214kB)
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf

Download (33kB)

Abstract

Decomposing a complex computational problem into sub-problems, which are computationally simpler to solve individually and which can be combined to produce a solution to the full problem, can efficiently lead to compact and general solutions. Modular neural networks represent one of the ways in which this divide-and-conquer strategy can be implemented. Here we present a co-evolutionary model which is used to design and optimize modular neural networks with task-specific modules. The model consists of two populations. The first population consists of a pool of modules and the second population synthesizes complete systems by drawing elements from the pool of modules. Modules represent a part of the solution, which co-operates with others in the module population to form a complete solution. With the help of two artificial supervised learning tasks created by mixing two sub-tasks we demonstrate that if a particular task decomposition is better in terms of performance on the overall task, it can be evolved using this co-evolutionary model. © 2005 IEEE.

Item Type: Conference or Workshop Item (Paper)
Additional Information: © 2005 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 12 Jul 2012 12:35
Last Modified: 23 Sep 2013 19:27
URI: http://epubs.surrey.ac.uk/id/eprint/532840

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800